Whether dynamic dimensional model transformation is supported?


After Converting the TensorFlow pb model to generate the onnx model, I found that the conversion failed when I needed to convert the engine model to it.

My model is a dynamic input, so I am not sure whether TensorRT7.2 supports the transformation of the dynamic input size model?


TensorRT Version: 7.2
GPU Type: 2080ti
Nvidia Driver Version: 440
CUDA Version: 10.2
CUDNN Version: 8.0
Operating System + Version: centos7
Python Version (if applicable): 3.6
TensorFlow Version (if applicable): 1.14
PyTorch Version (if applicable):
Baremetal or Container (if container which image + tag):

Relevant Files

model files:

The error message

Hi @1965281904,
Please check the below link to understand dynamic shapes.
Also you should try optimization profiles here.